ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Statistical class-based MFCC enhancement of filtered and band-limited speech for robust ASR

Nicolás Morales, Doroteo Torre Toledano, John H. L. Hansen, José Colás, Javier Garrido

In this paper we address the problem of bandwidth extension from the point of view of ASR. We show that an HMM-based recognition engine trained with full-bandwidth data can successfully perform ASR on limited-bandwidth test data by means of a simple correction scheme over the input feature vectors. In particular we show that results obtained using full-bandwidth HMMs and corrected feature vectors can be comparable to, or even outperform results obtained using limited-bandwidth-trained HMMs. Both results are inferior to those obtained with full-bandwidth HMMs and test data. These results suggest that the effect of channel mismatch on recognition accuracy can be partially compensated with a feature correction scheme, while the loss of information inherent to a limited-bandwidth cannot be compensated.


doi: 10.21437/Interspeech.2005-246

Cite as: Morales, N., Torre Toledano, D., Hansen, J.H.L., Colás, J., Garrido, J. (2005) Statistical class-based MFCC enhancement of filtered and band-limited speech for robust ASR. Proc. Interspeech 2005, 2629-2632, doi: 10.21437/Interspeech.2005-246

@inproceedings{morales05_interspeech,
  author={Nicolás Morales and Doroteo {Torre Toledano} and John H. L. Hansen and José Colás and Javier Garrido},
  title={{Statistical class-based MFCC enhancement of filtered and band-limited speech for robust ASR}},
  year=2005,
  booktitle={Proc. Interspeech 2005},
  pages={2629--2632},
  doi={10.21437/Interspeech.2005-246}
}